MCP Spine
Context Minifier & State Guard — Local-first MCP middleware proxy that reduces token waste by 61%, prevents context rot, and adds security hardeningRead full description
Donnyb369LABSCO SUMMARY
The token is in Vault, not in your config.
Two tokens looks like extra work until you see what it buys: the AI Guard credential lives in Pangea Vault with automatic rotation, and the config only carries a fetcher token and an item ID. The audit log is the other half — every screening decision is recorded, so a blocked message can be explained after the fact rather than just disappearing. It only wraps stdio servers, so remote ones need mcp-remote in between.
What it is
A proxy that sits between an MCP client and any MCP server, routing all tool input and output through Pangea AI Guard. You keep the server you were already using; the proxy is what the client launches, with the original command as its argument.
What you get
- Prompt injections blocked, including ones wrapped in a riddle
- Malicious links, IPs and domains caught, using CrowdStrike, DomainTools and WhoisXML threat intelligence
- 50 types of confidential information and PII detected
- 10 content filters covering toxicity, self harm, violence and topic-based filtering, across 104 spoken languages
- Your AI Guard token held in Pangea Vault with automatic rotation, rather than sitting in your client config
- Every AI Guard request and its detection results written to your Secure Audit Log, giving an immutable trail for audits and incident response
Requirements
Node.js v22.15.0 or greater, and two Pangea API tokens: one with access to AI Guard, stored in Pangea Vault, and one with Vault access used to fetch the first at runtime. In the client config, wrap the original command — npx -y @pangeacyber/mcp-proxy -- <original command and args> — and set PANGEA_VAULT_TOKEN to the Vault API token and PANGEA_VAULT_ITEM_ID to the Vault item holding the AI Guard token. Remote servers over HTTP or SSE need mcp-remote first to turn them into stdio. Binary name mcp-proxy.
Setup effort
One command plus a key — npx -y @pangeacyber/mcp-proxy, then supply credentials
USE CASES
01
Using a third-party MCP server you did not audit
Wrap its launch command so tool output is screened before it reaches the model.
02
Keeping PII out of an assistant's context
Let the guard's confidential-information detection run on both directions of the conversation.
03
Explaining an incident afterwards
Read the Secure Audit Log entries for the requests and detections rather than reconstructing what happened.
04
Protecting a remote server too
Put mcp-remote in front to convert HTTP or SSE to stdio, then wrap that with the proxy.
BEFORE YOU INSTALL
What to know first
Requires
- npx on PATH
- Node.js 22.15.0 or later
- PANGEA_VAULT_TOKEN in your environment
- PANGEA_VAULT_ITEM_ID in your environment
INSTALLATION
Connect your client
Add the block to your client, or run the command directly.
Server setup
Configuration file
JSON
{
"mcpServers": {
"qrcode": {
"command": "npx",
"args": [
"-y",
"@pangeacyber/mcp-proxy",
"--",
"npx",
"-y",
"@jwalsh/mcp-server-qrcode"
],
"env": {
"PANGEA_VAULT_TOKEN": "pts_00000000000000000000000000000000",
"PANGEA_VAULT_ITEM_ID": "pvi_00000000000000000000000000000000"
}
}
}
}npx
TERMINAL
npx -y @pangeacyber/mcp-proxy
